JP2017167725A - Patent requirement adequacy prediction device and patent requirement adequacy prediction program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To effectively reduce a monitoring burden on patent application by predicting the adequacy of patent requirements using contents in conformity to examination practice.SOLUTION: A patent requirement adequacy prediction server includes: gazette data extraction means; gist data extraction means for extracting, regarding a prediction object application identified by prediction object data, gist data allowing the gist of a prediction object invention to be determined from prediction object data; gist data storage means for storing the gist data; and patent requirement adequacy prediction processing means including a novelty prediction processing unit for generating novelty prediction data indicating the requirement adequacy of novelty of the prediction object invention, an inventiveness prediction processing unit for generating inventiveness prediction data indicating the requirement adequacy of inventiveness, and a prediction result file generation unit for generating a prediction result file indicating the patent requirement adequacy of the prediction object invention by using the novelty prediction data and the inventiveness prediction data.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a patent requirement conformity prediction apparatus and a patent requirement conformity prediction program for predicting whether or not a patent application such as novelty and inventive step is suitable for the invention relating to a patent application that has been published.

  Conventionally, prediction is performed in various scenes such as prediction of power demand and stock price, prediction of purchase of goods, and prediction of future price of real estate, and many apparatuses and methods have been proposed. A technology for predicting patentability (also referred to as patentability or patentability) relating to an applied invention has also been proposed with respect to a right-giving operation for applying a patent for an invention (see, for example, Patent Document 1). Patent Document 1 describes the following patentability prediction apparatus. This device obtains a patent application (notified application) that has been notified of examination results from the patent database, detects the amount of information about the claims of the already-notified application, and the number of similar prior applications, and The target regression analysis is executed, and the predicted value of the patentability of the application for which the examination result is not notified is calculated according to the registration prediction formula calculated from these.

  Conventionally, in addition to prediction of patentability, devices and methods for evaluating the patentability and quality of an invention, the value of patent applications and patent rights have also been proposed (for example, Patent Documents 2, 3, 4, and 4). 5 and 6).

JP 2009-238074 A JP2015-207194A JP 2000-181966 A JP 2000-132606 A Japanese Patent Laying-Open No. 2015-187883 JP 2007-108803 A

  As described above, according to the prior art, it is possible to predict the patentability and evaluate the patent right for a patent application.

  However, in the above-described conventional technology, for example, the patentability prediction apparatus described in Patent Document 1, the patentability prediction is calculated based on information such as the amount of information about the claims of a previously notified application and the number of similar prior applications. This is done according to the registration preview formula. This prediction was made based on a statistical correlation between the breadth of claims, the density of technical fields, and patentability, and was not based on patent law or patent / utility model examination standards. Therefore, the patentability prediction apparatus described in Patent Document 1 has a problem that there is a high possibility that a prediction result in accordance with the patent practice cannot be obtained.

  By the way, in general, what kind of patent applications other companies are applying for and what kind of patent rights they are trying to acquire is a serious concern for the company. For this reason, there are not a few cases in which patent rights are obtained by monitoring not only the company's own patent application but also patent applications of other companies. In order to make such predictions, it is necessary to read application documents, conduct prior art searches, and determine whether the patent requirements are appropriate.

  In this regard, if a patentability prediction apparatus such as the prior art is used, the patentability of an application for which an examination result has not been notified can be predicted.

  However, the examination of patent requirements is conducted by the JPO examiner in accordance with the Patent Law and Patent / Utility Model Examination Standards (Patent Law Article 47). May not be compatible and therefore not effective in reducing the monitoring burden of patent applications.

  Therefore, it has been desired to reduce the monitoring burden of a patent application as effectively as possible by predicting whether or not it conforms to patent requirements with a content that conforms to examination practice.

  The present invention has been made in order to solve the above-mentioned problems, and the prediction regarding the propriety of the patent requirement is performed with the content suitable for the examination practice, and the patent requirement conformity prediction device capable of effectively reducing the monitoring burden of the patent application and It is an object of the present invention to provide a patent requirement conformity prediction program.

  In order to solve the above problems, the present invention provides a publication data extraction means for extracting prediction target data corresponding to a designated number from a publication gazette data storage unit in which electronic data of a published patent publication is stored as publication gazette data. And, for the prediction target application specified by the prediction target data extracted by the publication data extraction means, term data indicating terms that can specify the gist of the prediction target invention disclosed in the prediction target application, Summary data extraction means for extracting from the data to be predicted as summary data data including at least feature part data extracted from the feature part of each claim and problem data extracted from the column of the problem to be solved by the invention; and Abstract data storage means for storing abstract data extracted by the abstract data extraction means, and abstract data storage means A novelty prediction processing unit that searches public gazette data using summary data stored in the database, and generates novelty prediction data indicating whether the novelty requirement of the invention to be predicted is appropriate according to the search result; An inventive step prediction processing unit for generating inventive step prediction data indicating whether or not the requirement of the subject invention is necessary, and a prediction result file indicating the suitability of the patent requirement of the subject invention using the novelty prediction data and the inventive step prediction data A patent requirement suitability prediction processing unit having a prediction result file generation unit to generate, and the inventive step prediction processing unit is a main cited invention closest to the prediction target invention among the prior art inventions specified by the publication data A main citation invention search unit and a document classification unit for classifying document vectors. The main citation invention search unit stores summary data stored in the summary data storage means. The main reference invention is the most similar document that has the highest similarity as a result of the concept search. Whether the document classification unit conforms to the requirement for inventive step by machine learning using a plurality of training data including a learning document vector and a teacher vector. It is constructed so as to be classified into any of the above and a requirement conformity document vector corresponding to the classification result is output, and the abstract movement vector is the abstract vector corresponding to each claim of the prediction target application and the most similar document It is characterized by a patent requirement suitability prediction device which is a vector corresponding to a difference from a citation candidate vector corresponding to.

  Further, the present invention provides a publication data extraction means for extracting prediction target data corresponding to a designated number from a publication gazette data storage unit in which electronic data of a published patent publication is stored as publication publication data, and publication data Term data that indicates terms that can identify the gist of the invention to be predicted disclosed in the application to be predicted, which is specified by the data to be predicted extracted by the extraction means, and at least each claim Abstract data extracting means for extracting data including characteristic part data extracted from the characteristic parts of the present invention and problem data extracted from the problem column to be solved by the invention from the data to be predicted as abstract data, and the abstract data extracting means The abstract data storage means for storing the abstract data extracted by the means and the abstract data storage means The novelty prediction processing unit that searches the public gazette data using the abstract data and generates the novelty prediction data indicating the suitability of the novelty requirement of the prediction target invention according to the search result, and the progress of the prediction target invention A prediction result generation unit that generates the inventive step prediction data indicating whether or not the requirements of the invention are appropriate, and a prediction result file that generates the prediction result file indicating the suitability of the patent requirements of the invention to be predicted using the novelty prediction data and the inventive step prediction data A patent requirement propriety prediction processing means having a file generation unit, and the inventive step prediction processing unit searches for a main cited invention that is closest to the prediction target invention among the prior art inventions specified by the publication data. The invention includes a citation invention search unit and a document classification unit that classifies document vectors, and the main citation invention search unit includes a summary data stored in the summary data storage unit. A concept search is performed on public gazette data using the collection part data and task data as the main search document data, and as a result of the concept search, a plurality of documents including the most similar document with the highest similarity in descending order of similarity Extracted as similar documents, and each similar document as the main cited document in which the main cited invention is disclosed, the document classification unit, by machine learning using a plurality of training data including a learning document vector and a teacher vector, The input summary movement vector is classified into either a class that is highly unlikely to meet the inventive step requirement, a high class, or a class that meets the inventive step requirement, and the requirement conformance document vector according to the classification result The abstract movement vector includes an abstract vector corresponding to each claim of the application to be predicted, and a citation candidate vector corresponding to each similar document. The patent requirement conformity prediction processing means does not conform to the inventive step requirement for the prediction target application according to the plurality of requirement conformity document vectors output from the document classification unit. There is provided a patent requirement conformity prediction apparatus further including a non-conformance rate calculation unit for calculating a non-conformance rate indicating possibility.

  In the case of the above-mentioned patent requirement conformity prediction apparatus, the document classification unit uses training data as a combination of a learning document vector as a first learning document vector and a teacher vector as a vector indicating that there is a reason for rejection of novelty and inventive step, The combination of the document vector is the second learning document vector and the teacher vector is a vector indicating that there is a reason for refusal of inventive step and there is no reason for refusal of novelty, and the learning document vector is the third learning document vector and the teacher vector is inventive. Is used in combination with a vector indicating that there is no reason for refusal, and the first learning document vector is an application for which a notice of reason for refusal has been issued among already published applications, The reason for refusal of a novelty / inventive step rejection application was pointed out by citing the same document and the reason for refusal without novelty and inventive step was pointed out A first moving document vector corresponding to a difference between a document vector corresponding to a request and a first cited document vector corresponding to a first main cited publication which is a document cited for the reason for refusal The second learning document vector is an application for which a notice of reason for refusal has been issued in the published application, and the reason for refusal of novelty is not pointed out in the notice of reason for refusal, but the reason for refusal of inventive step is pointed out The document vector corresponding to the claim in which the reason for refusal of the inventive stepped rejection application was pointed out, and the second corresponding to the second main cited publication cited as the main publication for the reason for refusal A second moving document vector corresponding to a difference from the cited document vector, and the third learning document vector is a non-rejection application in which a patent decision is issued without a notice of reason for refusal being issued in the published application or Issuing reason for rejection A document vector according to claim 1 of a non-inventive refusal application for which the reason for refusal of refusal was not pointed out in the notice of reasons for refusal, and an application without refusal or an application without inventive step refusal As a result of the concept search, it is possible to obtain a patent requirement conformity prediction apparatus that is a third moving document vector obtained from a difference from a non-cited document vector corresponding to the most similar document for learning that has the highest similarity. .

  Furthermore, the present invention is a patent requirement suitability prediction program for causing a computer to function as a patent requirement suitability prediction device, wherein the computer is a public gazette data storage unit in which electronic data of a published patent gazette is stored as public gazette data. From the publication data extraction means for extracting the prediction target data corresponding to the designated number, and the prediction target application specified by the prediction target data extracted by the publication data extraction means, the prediction target application is disclosed. Term data indicating terms that can identify the gist of the invention to be predicted, and at least feature part data extracted from the feature part of each claim and problem data extracted from the problem column to be solved by the invention Abstract data extraction means for extracting the data including the abstract data from the prediction target data, and its The gazette data storage control means for storing the gist data extracted by the essence data extraction means and the gazette data stored by the control of the gist data storage control means are used to search the public gazette data, and according to the search result A novelty prediction processing unit that generates novelty prediction data indicating whether the novelty requirement of the prediction target invention is appropriate; and an inventive step prediction processing unit that generates inventive step prediction data indicating whether the inventive step requirement is appropriate And a prediction result file generation unit that generates a prediction result file that indicates whether or not the patent requirement of the invention to be predicted is satisfied by using the novelty prediction data and the inventive step prediction data. Among the prior art inventions whose processing unit is specified by the publication gazette data, the main citation invention test for searching the main citation invention closest to the prediction target invention Characteristic data and problem data of each claim of the gist data stored in the main citation invention search unit under the control of the gist data storage control means The main search document data is used as a main search document data, and a concept search is performed on public gazette data. As a result of the concept search, the most similar document with the highest similarity is set as the main reference document in which the main cited invention is disclosed, and the document The classification unit classifies the input summary movement vector according to the inventive step requirement by machine learning using a plurality of training data including a learning document vector and a teacher vector, and classifies the classification. It is constructed so as to output a requirement conformity document vector according to the result, and its summary movement vector is a summary vector corresponding to each claim of the prediction target application and a reference corresponding to the most similar document. A patent requirement suitability prediction program that is a vector corresponding to a difference from a candidate vector for use is provided.

  As described above in detail, according to the present invention, the prediction regarding the propriety of the patent requirement is performed with the content suitable for the examination practice, and the patent requirement conformity prediction device and the patent requirement propriety that can effectively reduce the monitoring burden of the patent application. A prediction program is obtained.

1 is a system configuration diagram of a patent requirement suitability prediction system including a patent requirement suitability prediction server according to a first embodiment of the present invention. It is a block diagram which mainly shows the internal structure of a patent requirement suitability prediction server. It is a block diagram which mainly shows the internal structure of a user terminal device. It is a functional block diagram which shows the main structures of the patent requirement suitability prediction server which concerns on the 1st Embodiment of this invention. It is a functional block diagram which shows the main structures of an abstract data extraction part. It is a functional block diagram which shows the main structures of the patent requirement suitability prediction process part which concerns on the 1st Embodiment of this invention. It is a functional block diagram which shows the main structures of an input vector production | generation part. It is a figure which shows an example of the record layout of a summary data storage part. It is a figure which shows an example of the record layout of CT data storage part. It is a figure which shows an example of the record layout of a prediction result memory | storage part. It is a figure which shows an example of the network structure of a machine learning part. It is a flowchart which shows an example of the operation | movement procedure of a patent requirement suitability prediction process. It is a flowchart which shows an example of the operation | movement procedure of a patent requirement suitability prediction routine. It is a flowchart which shows an example of the operation | movement procedure of a novelty and expansion prior application prediction routine. It is a flowchart which shows an example of the operation | movement procedure of an expansion prior application prediction routine. It is a flowchart which shows an example of the operation | movement procedure of an inventive step prediction routine. It is a flowchart which shows an example of a single independent term routine. It is a flowchart which shows an example of the operation | movement procedure of a multiple independent term routine. It is a flowchart which shows an example of an independent term search process. It is a flowchart which shows an example of main citation invention search processing. It is a flowchart which shows an example of a subcitation invention search process. It is a flowchart which shows an example of a dependent term search process. It is the figure which showed typically the relationship between the patent application used as examination object, and several patent publications. It is a figure which shows an example of the record layout of an independent item table. It is a figure which shows an example of a patent requirement suitability prediction list. It is a functional block diagram which shows the main structures of the patent requirement suitability prediction server which concerns on the 2nd Embodiment of this invention. It is a functional block diagram which shows the main structures of the patent requirement suitability prediction process part which concerns on the 2nd Embodiment of this invention. It is a functional block diagram which similarly shows the main structures of an input vector production | generation part. It is a figure which similarly shows an example of the record layout of a prediction result memory | storage part. It is a figure which similarly shows an example of a patent requirement suitability prediction list. It is a functional block diagram which shows the main structures of the patent requirement suitability prediction process part which concerns on a modification.

  Embodiments of the present invention will be described below with reference to the drawings. In addition, the same code | symbol is used for the same element and the overlapping description is abbreviate | omitted.

First embodiment
(Overall structure of patent requirement conformity prediction system)
First, the configuration of the patent requirement suitability prediction system 1 including the patent requirement suitability prediction server 10 according to the first embodiment of the present invention will be described.

  FIG. 1 is a system configuration diagram of a patent requirement suitability prediction system 1. As shown in FIG. 1, the patent requirement suitability prediction system 1 has a patent requirement suitability prediction server 10 and a plurality of user terminal devices 30 (in FIG. 1, fixed terminal devices 30A, 30B, and 30C) operated by the user. These are connected to each other via the Internet N1.

  The patent requirement conformity prediction server 10 performs data processing according to the patent requirement conformity prediction program, and among the published patent applications (hereinafter referred to as “published applications”), the application publication number (or application number) designated by the user. For patent applications (applications to be predicted) according to the requirements, patent requirements (in this embodiment, novelty (Patent Act Article 29, Paragraph 1, Item 3), extended prior application (Patent Act Article 29-2) and inventive step) (Patent Act Article 29 Paragraph 2)) is predicted. The user terminal device 30 receives or transmits data with the patent requirement suitability prediction server 10.

  In the patent requirement suitability prediction system 1, the patent requirement suitability prediction server 10 performs a main citation invention search and a sub-citation invention search, which will be described later, for a prediction target application, and also has a high or low possibility of finding a reason for refusal of inventive step violation. This is predicted by an artificial intelligence program that performs machine learning with a plurality of training data based on examination results, and predicts the suitability of patent requirements. Since the patent requirement conformity prediction server 10 predicts the suitability of the patent requirement with the content suitable for the examination practice, the monitoring burden of the patent application can be effectively reduced.

(Configuration of Patent Requirements Compliance Predicting Server 10)
Next, the configuration of the patent requirement suitability prediction server 10 will be described with reference to FIG. FIG. 2 is a block diagram centering on the internal configuration of the patent requirement suitability prediction server 10. The patent requirement conformity prediction server 10 is a server operated by a specialized business operator that provides a service relating to prediction of patent requirement conformance of a published application.

  The patent requirement conformity prediction server 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, and a RAM (Random Access Memory) 13. The CPU 11 operates in accordance with a program stored in the ROM 12 and inputs input data obtained by operation input of the keyboard 19 and the mouse 20 via the KBC (Key board controller) 17 via the main bus 19A. Input / output of signals to / from other components is performed to control the operation of the patent requirement conformity prediction server 10 as a whole. The CPU 11 operates as a gazette data extraction unit 101, a gist data extraction unit 102, a patent requirement suitability prediction processing unit 103, a target gazette extraction unit 104, and a prediction result editing processing unit 105, which will be described later, according to a patent requirement suitability prediction program described later. I do. The ROM 12 stores a control program executed by the CPU 11 such as a patent requirement suitability prediction program and permanent data. The RAM 13 stores data and programs used when the CPU 11 operates.

  In addition, the patent requirement compliance prediction server 10 includes a hard disk drive (HDD) 14, a communication control unit 15, a communication processing unit 16, and a video controller 18.

  The hard disk device 14 is formed with various storage units or DBs (database) shown in FIG. 4 and other storage units or DBs necessary for executing the patent requirement suitability prediction program. The hard disk device 14 includes a designated number transaction storage unit (designated number TR storage unit) 151, a prediction target transaction storage unit (prediction target TR storage unit) 152, a gist data storage unit 153, and a claim tree data storage unit 154. A target publication storage unit 155 and a prediction result file storage unit 156 are formed. Each storage unit or DB will be described later.

  The communication control unit 15 operates in accordance with an instruction from the CPU 11 to control connection and disconnection of a line for performing communication with the user terminal device 30 and a patent office server (not shown). The communication processing unit 16 operates according to an instruction from the communication control unit 15 and executes data transmission / reception performed via the Internet N1.

  The video controller 18 controls image display on a display device (not shown) to display a screen used for various settings.

  The various storage units or DBs of the hard disk device 14 will be described as follows. In the designated number TR storage unit 151, data (for example, a member ID) necessary for user identification transmitted from the user terminal device 30 and an application publication number or application number designated by the user (these are referred to as “designated numbers”). ) Is stored. The prediction target TR storage unit 152 stores application document electronic data (prediction target data) of the prediction target application extracted by the gazette data extraction unit 101 from the publication gazette DB 150 according to the designated number. The public gazette DB 150 stores the electronic data of the published patent gazette as public gazette data. As the public gazette DB 150, FIG. 4 assumes a database of a patent information platform (J-PlatPat) operated by the industrial property information / training hall or a database storing electronic data downloaded therefrom. The latter database can be stored in a server (not shown) or may be stored in the HDD 14.

  The summary data storage unit 153 stores summary data extracted and generated by the summary data extraction unit 102. The gist data is term data indicating terms that can specify the gist of the invention (prediction target invention) disclosed in the prediction target application, and includes at least characteristic part data and problem data described later.

  For example, as shown in FIG. 8, the abstract data storage unit 153 stores a record having a data type area 153a, an item number area 153b, and a term storage unit 153c. The data type area 153a stores data (referred to as “data type”) indicating which part of the prediction target application the data stored in each record is. In the present embodiment, four types, “C”, “P”, “T”, and “D”, are set as data types. “C” is data in the claims, “P” is data in the column of the problem to be solved by the invention, “T” is data in the column of the technical field, and “D” is in the column of the embodiment of the invention Each data is shown. The number of the claim is stored in the item number area 153b. The term storage unit 153c has a term area 153c1, a development degree area 153c2, and an essential flag area 153c3. In FIG. 8, 15 combinations of these are prepared, but there may be more or less than 15 combinations. In the term area 153c1, the development degree area 153c2, and the essential flag area 153c3, terms used for specifying the gist, a later-described development degree (Ed), and an essential flag (Ef) are stored.

  In FIG. 8, as an example, summary data (upper half data) extracted from JP 2008-62282 A and summary data (lower half data) extracted from JP 2011-186735 A are described. Yes. The former is an example when there is one claim (independent claim) described in an independent form, and the latter is an example when there are a plurality of independent claims.

  The claim tree data storage unit (CT data storage unit) 154 stores claim tree data (also referred to as claim tree data or CT data) to be described later. In the CT data storage unit 154, for example, as shown in FIG. 9A, a record including an independent division area 154a, a number area 154b, a MAX division area 154c, a dependent item area 154d, and a search flag area 154e. It is remembered.

  In the independent division area 154a, an independent division indicating whether each claim of the prediction target application is an independent claim or a claim (dependent claim) described in a dependent format (independent claim is space, dependent claim is "D") is stored. In the number area 154b, the number of each claim (claim number) is stored. The MAX division area 154c stores a MAX division. In the MAX section, “M” is set in the claim with the largest number (maximum dependent claim) when there are a plurality of dependent claims that refer to the same independent term, and a space is set in addition to that.

  FIG. 9A shows CT data of Japanese Patent Application Laid-Open No. 2008-62282. In this publication, since claim 9 is the maximum dependent claim among the dependent claims, the record whose claim number is “9”. "M" is set in the MAX section, and a space is set in the MAX section of the other claim numbers. FIG. 9B shows CT data of Japanese Patent Application Laid-Open No. 2011-186735. In this publication, claims 1 and 6 are independent claims, and claims 5 and 7 are Since it is the maximum dependent term, “M” is set in the MAX division of the record whose claim number is “5” and “7”, and a space is set in the MAX division other than these.

  In the dependent claim area 154d, the number of the claim cited by the dependent claim is stored. The search flag area 154e stores a search flag, that is, a classification indicating whether or not a later-described main citation invention search has been executed. A space indicates before execution of the main cited invention search, and “9” indicates execution completed.

  The target publication storage unit 155 stores public gazette data (search target publication data) to be searched for the main citation invention search and the sub-citation invention search. The prediction result storage unit 156 stores a prediction result file described later as shown in FIG.

  Next, the summary data extraction unit 102 and the patent requirement suitability prediction processing unit 103 will be described. As shown in FIG. 5, the summary data extraction unit 102 includes a candidate extraction unit 111, a main data extraction unit 112, a CT data generation unit 113, a text analysis / term extraction unit 114, a development level / essential requirement analysis unit 115, A receiving analysis unit 116, a pattern data extraction unit 117, and a file generation unit 118 are included. For convenience of illustration, in FIG. 5, a detailed explanation data storage unit (detailed description TR) 160, a claim data storage unit (claims TR) 161, a main data storage unit (main data TR) 162 are included in the summary data extraction unit 102, and these are provided in the HDD 14 serving as data storage means.

  The candidate extraction unit 111 reads the prediction target data stored in the prediction target TR storage unit 152, skips unnecessary data from the prediction target data, extracts data necessary for the creation of summary data, The data is divided into detailed explanation data (specification data) and claims data, and stored in the detailed explanation TR160 and claims TR161, respectively. Here, “the above”, “the”, “the” and the paragraph numbers are skipped.

  The main part data extraction unit 112 reads the prediction target data stored in the prediction target TR storage unit 152, extracts the data (main part data) corresponding to the main part of the specification, and extracts the extracted main data. The part data is stored in the main part data storage unit 162. Here, as the main part data, the data in the “Title of Invention” column (name of the invention) and the data in the “Technical Field” column of the specification, and the “Problem to be Solved by the Invention” column are displayed. One sentence data including the character string of the present invention or the present invention is extracted.

  The CT data generation unit 113 reads the prediction target data stored in the prediction target TR storage unit 152, reads the data described in the column of the claims, and the above-described claim tree data (CT data) Is generated and stored in the CT data storage unit 154.

  The text analysis / term extraction unit 114 inputs text data from the detailed description TR160 and the claims TR161, extracts feature words for each of them (the claims are for each claim), and each feature word Are output in the important order. In this case, for example, index character string extraction processing such as morphological analysis or N-Gram is executed to check the appearance frequency of each word and the co-occurrence frequency of each word, and output each feature word according to the result.

  The development level / essential requirement analysis unit 115 reads the claim data from the claim range TR161, and for each feature word extracted by the text analysis / term extraction unit 114, whether the development level and the essential requirements are met. Check whether or not, and output the result. Here, the degree of expansion (Ed) is data indicating how many claims each feature word is expanded (used) and the number of claims expanded. In general, in an application for a patent application, more important matters are set forth in claim 1 (or other independent claims) in a broad range so that the broadest possible inventive concept is covered, and claims subordinate thereto. In many cases, it is described while the range is reduced (embraced) step by step. Therefore, it is considered that the greater the degree of development (Ed), the higher the degree of importance. Therefore, the degree of development is considered to be useful information for grasping the gist of the invention. For example, the term “punch” is set in the area of “term 1” in the term area 153c1 of data type “C” and item number “1” shown in FIG. In the scope of claims of Japanese Patent Application Laid-Open No. 2008-62282, since it is described in claims 1, 2, 3, 4, and 5, "5" is set in the expansion degree area 153c2.

  Whether or not it meets the essential requirements is whether or not it is described in the characteristic part of each claim and is indicated by an essential flag (Ef). In the embodiment of the invention according to the present application, the last paragraph in each claim or a sentence including the character string of “characteristic” is used as the feature part of each claim, and the data is the feature part data. , The terms included here shall meet the essential requirements. For the term extracted from the feature portion, “X” indicating that the essential requirement is satisfied is set in the essential flag (Ef).

  The dependency analysis unit 116 performs dependency analysis on the main data stored in the main data storage unit 162 and outputs the result to the pattern data extraction unit 117.

  The pattern data extraction unit 117 inputs the analysis result of the dependency analysis unit 116, and the noun immediately before the hiragana character “O”, the character string that is the combination of the corresponding verb, and the beginning of the name of the invention (First name) is output. For example, in a sentence including the character string “present invention” in the column “Problem to be Solved by” of Japanese Patent Application Laid-Open No. 2008-62282, the noun immediately before “O” in hiragana and the corresponding Verb combinations include “adjustment” and “do not do”, “concentricity” and “obtain”, “precision punching” and “provide”. These are output from the pattern data extraction unit 117. In the present embodiment, among the data output from the pattern data extraction unit 117, the data extracted from the “problem to be solved by the invention” column corresponds to the problem data. For example, the data type of FIG. Data such as a record of “P” can be used.

  The file generation unit 118 generates summary data using data output from the text analysis / term extraction unit 114, the development level / essential requirement analysis unit 115, and the pattern data extraction unit 117, and stores the summary data in the summary data storage unit 153. In this case, data of the data types “C” and “D” is generated using the output data of the text analysis / term extraction unit 114 and the development level / essential requirement analysis unit 115, and the output data of the pattern data extraction unit 117 is used as the output data. As a result, data of data types “P” and “T” is generated.

  As shown in FIG. 6, the patent requirement suitability prediction processing unit 103 includes a novelty / expansion prior application prediction processing unit 125 and an inventive step prediction processing unit 126. The novelty / expanded prior application prediction processing unit 125 uses the summary data stored in the summary data storage unit 153 as a search term to perform a full text search of the search target publication data in the target publication storage unit 155, and according to the result. The novelty / expansion prior application prediction data Nd is output to the prediction result file generation unit 127. The function and operation procedure of the novelty / expansion earlier application prediction processing unit 125 will be described in detail later.

  The inventive step prediction processing unit 126 includes a cited invention search unit 131, an input vector generation unit 132, and a machine learning unit 133. The cited invention search unit 131 has a main cited invention search unit that performs a main cited invention search and a subcited invention search unit that performs a subcited invention search, which will be described later. In addition, the cited invention search unit 131 outputs the inventive step prediction data Vd1 to the prediction result file generation unit 127 according to the results of the main cited invention search and the sub-cited invention search, and responds to the claim that is the target of the search. Claim summary data ied and concept search data Vd 2 are output to input vector generation section 132. The concept search data Vd2 includes publication gazette data of a document (the most similar document) that is determined to have the highest similarity as a result of the concept search. The function and operation procedure of the cited invention search unit 131 will be described in detail later.

  As shown in FIG. 7, the input vector generation unit 132 includes a summary vector generation unit 132a, a citation candidate vector generation unit 132b, and a movement vector generation unit 132c.

  The summary vector generation unit 132a receives the claim summary data ied, extracts the feature words, performs weighting according to each word, and generates the summary vector EV according to the description of each claim. The citation candidate vector generation unit 132b inputs public gazette data of the most similar document included in the concept search data Vd2, extracts the feature word, performs weighting according to each word, and performs document weighting according to the most similar document (Quotation candidate vector) RfV is generated. The movement vector generation unit 132c calculates a difference between the abstract vector EV and the citation candidate vector RfV, and generates an abstract movement vector V3 according to the difference between the two document vectors.

  Since the most similar document is a document having the highest similarity as a result of the concept search by the main citation invention search unit, the probability of being cited as a disclosure document of the main citation invention in the inventive step examination of the prediction target invention is high. Presumed to be the highest. Therefore, if the citation candidate vector RfV is obtained using the most similar document as a citation candidate and the difference between the citation candidate vector RfV is calculated and the gist movement vector V3 is obtained, the invention to be predicted and the invention disclosed in the most similar document A document vector (corresponding to the abstract movement vector V3) corresponding to the difference is generated.

  The machine learning unit 133 is a document classification unit according to the embodiment of the present invention, and a summary movement vector described later by machine learning (supervised learning) using the following training data (also referred to as a learning pattern). It is constructed to classify V3 into a class that conforms to the requirement of inventive step and a class that does not conform (class that has no reason for refusal) and output an output signal (requirement conformity document vector) V4 according to the classification result. ing. In the embodiment of the present invention, the learning pattern can be an HL pattern described below.

  In the HL pattern, the learning document vector is the first learning document vector, and the teacher vector is a vector indicating that there is a reason for rejection of the inventive step (for example, only the dimension corresponding to the correct class is “1” and the others are “0”). Vector), the learning document vector is the second learning document vector, and the teacher vector is a vector indicating that there is no reason for rejection of the inventive step (for example, only a dimension different from the above is “1” and the others are “0”). Is a combination pattern with "vector".

  The first learning document vector is an application for which the first notice of reasons for refusal (1st action) has been issued as a result of examination by the Patent Office in a published application, and the reason for refusal of inventive step violation ( Claims (at the time of issuance of the notice of reasons for refusal) that pointed out the reasons for refusal of the application (reasonable refusal application) for which the reason for refusal that the requirements of Article 29 (2) of the Patent Act were not satisfied Is a first moving document vector corresponding to a difference between a document vector corresponding to the document vector and a document vector (cited document vector) corresponding to the cited document 1 (main cited document cited as the main publication) at that time. .

  The second learning document vector is the result of examination in the published application that the patent action is issued without the first action being issued (the application without refusal) or the first action is issued but the reason for refusal is advanced Document vectors according to claim 1 (at the time of the notice of reasons for refusal) of applications for which no reason for refusal of sex violation has been pointed out (applications without inventive refusal), and those applications without refusal or inventive refusal As a result of the concept search for the application, the second moving document vector corresponding to the difference from the document vector (non-cited document vector) corresponding to the document (the most similar document for learning) that has the highest similarity is used. is there.

  The machine learning unit 133 classifies the abstract movement vector V3 into either a class with or without a reason for refusal of inventive step by repeatedly performing learning with the learning pattern of the HL pattern as described above, and the class is classified into the classified class. A corresponding requirement conformity document vector V4 is output. The former corresponds to a case where the reason for refusal of inventive step violation is likely to be issued for the forecast application, and the latter corresponds to a low case.

  The machine learning unit 133 may classify the inputted abstract movement vector V3 into a class having a reason for refusal of inventive step and a class having no reason for refusal of inventive step, and output a requirement conformity document vector V4 according to the classification result. A learning algorithm called a support vector machine (SVM) can be applied to the unit 133. According to the support vector machine (SVM), the decision boundary can be obtained so that the distance (margin) from the decision boundary is maximized.

  In addition, a neural network modeled on the brain neural network can be applied to the information processing of the machine learning unit 133. Neural networks include hierarchical neural networks and interconnected neural networks. For example, a perceptron of a hierarchical neural network can be applied as a learning algorithm of the machine learning unit 133.

  The perceptron is composed of a three-layer hierarchical network called S layer, A layer, and R layer (not shown), and there is only one-way coupling from S layer to A layer and from A layer to R layer. . Given the learning pattern of the HL pattern described above, when the output vector when the first learning document vector or the second learning document vector is input is different from each teacher vector, according to the error. The learning ends when the weight of the connection is corrected and the error between the output vector and the teacher vector becomes a certain value or less.

  However, the perceptron may not stop the algorithm when the learning pattern cannot be linearly separated. Therefore, in order for the machine learning unit 133 to acquire a non-linear decision boundary by learning, there are many application examples in a hierarchical neural network, and a BP (back propagation) network that can learn a non-linear discriminant plane with few misidentifications. Is preferably applied.

  As shown in FIG. 11, the BP network has an input layer and an output layer, and an intermediate layer therebetween, and a learning algorithm called an error back-propagation algorithm makes it possible to learn the weights of all the connections between units. ing. In the error back-propagation algorithm, the input signal is transmitted to the input layer, the intermediate layer, and the output layer, while the error signal is transmitted in the reverse direction, whereby weight adjustment is performed.

Then, when a learning pattern x _p (x ₀ , x ₁ ... X _n ) is input to the BP network shown in FIG. 11, the j (0 ≦ j ≦ n) -th unit in a certain hierarchy A weighted signal is input from the unit one layer before having a connection with the unit j. Therefore, if the signal from the i-th unit (0 ≦ i ≦ n) of the previous layer is t _ip and the weight is w _ij , the input to the unit j is given by Equation 1, and the output of the unit j is Suppose f is a threshold function and Equation 2 is obtained.

Formula 1

Formula 2

Error D _p for learning pattern x _p is the output of unit k of output layer, since is defined by the sum of squares of the difference between the teacher signal b _kp, so equation 3 below. The error D _p 3GS sum for all learning patterns sought D of formula 4, as its D is minimized, is adjusted connection weights between units is learning in machine learning unit 133 is carried out. In this case, each time an individual learning pattern is input, the weight is adjusted by Expression 5. w _ij is a weight before update, w ′ _ij is a weight after update, and ρ is a learning coefficient. This is called stochastic steepest descent. Note that the sigmoid function shown in Equation 6 is used as the unit input / output function.

Formula 3

Formula 4

Formula 5

Equation 6

(Configuration of the user terminal device 30)
As shown in FIG. 1, the user terminal device 30 includes a connection environment to the Internet N <b> 1 and can communicate with the patent requirement suitability prediction server 10. The user terminal device 30 is assumed to be a stationary (or portable notebook type) personal computer, but may be a tablet-type terminal device.

  As illustrated in FIG. 3, the user terminal device 30 includes a CPU 31, a ROM 32, a RAM 33, a data storage unit 34, and a liquid crystal display unit 35. In addition, the user terminal device 30 includes a voice conversion processing unit 36, a communication control unit 37, a communication processing unit 38a, a wireless communication unit 38b, a speaker 39, and a microphone 40.

  The CPU 31 operates according to a program stored in the ROM 32 and controls operation of the entire user terminal device 30. The ROM 32 stores a program executed by the CPU 31, for example, a communication control program for performing data communication. The RAM 33 stores data necessary for the CPU 31 to execute the program.

  Various data are stored in the data storage unit 34. The liquid crystal display unit 35 includes an LCD (Liquid Crystal Display) and its driving unit, and is an image display unit that displays images of characters, figures, symbols, and the like. The voice conversion processing unit 36 decompresses the voice data and outputs it to the speaker 39, while converting and compressing the analog voice signal input from the microphone 40 into digital voice data and inputs the digital voice data to the communication processing unit 38a. The communication control unit 37 operates in response to an instruction from the CPU 31 and controls connection and disconnection of a line for performing data communication. The communication processing unit 38a operates according to an instruction from the communication control unit 37, and executes transmission / reception of data performed via the Internet N1. The wireless communication unit 38b is a wireless communication unit that performs wireless data transmission / reception under the control of the communication control unit 37. The speaker 39 is an audio output means for outputting audio, and the microphone 40 inputs audio such as the user's conversation content and converts it into an electrical signal.

(Operations of the patent requirement conformity prediction system)
Next, referring to FIGS. 12 to 22 together with FIG. 4, the operation content of the patent requirement suitability prediction process by the patent requirement suitability prediction server 10 will be described.

  Here, FIG. 4 is a functional block diagram showing a main configuration of the patent requirement suitability prediction server 10 for realizing the patent requirement suitability prediction process. In the patent requirement suitability prediction server 10, the CPU 11 follows the patent requirement suitability prediction program while accessing various files and DBs stored in the publication gazette DB 150, summary data storage unit 153, etc. The extraction unit 102, the patent requirement suitability prediction processing unit 103, and the prediction result editing processing unit 105 are operated. Thereby, a patent requirement suitability prediction process is executed. The patent requirement suitability prediction program is a program for causing the patent requirement suitability prediction server 10 to function as the gazette data extraction unit 101, the gist data extraction unit 102, the patent requirement suitability prediction processing unit 103, the prediction result editing processing unit 105, and the like. is there.

  When the patent requirement suitability prediction server 10 performs the patent requirement suitability prediction process, the CPU 11 performs an operation according to the flowchart shown in FIG. 12 according to the patent requirement suitability prediction program. FIG. 12 is a flowchart showing an example of the operation procedure of the patent requirement suitability prediction process of the CPU 11 according to the patent requirement suitability prediction program. In FIG. 12, FIG. 13, etc., “S” is an abbreviation of step.

  When starting the operation according to the patent requirement suitability prediction program, the CPU 11 proceeds to step 1 and performs user authentication processing. Here, the user authentication process is performed by confirming the user ID and password input by the user using the user terminal device 30. Next, the CPU 11 proceeds to step 2 to perform a point balance confirmation process. Here, the CPU 11 checks whether or not the user's point balance is equal to or greater than a certain value. If the point balance is insufficient, the patent requirement suitability prediction process is terminated or a message notifying that the point balance is insufficient is transmitted.

  Subsequently, the CPU 11 proceeds to step 3, transmits the input screen data of the designated number to the user terminal 30, and waits for the input of the designated number of the user. Here, when a designated number is input, the designated number is stored in the designated number TR storage unit 151, and the number of designated numbers entered (for example, 3) is set in the publication counter MAX. Set 0 ".

  Next, the CPU 11 proceeds to step 4 to determine whether or not a prediction end condition is satisfied. Here, the CPU 11 proceeds to step 6 when the prediction end condition is satisfied, but proceeds to step 5 otherwise. When proceeding to step 5, the CPU 11 executes a patent requirement suitability prediction routine which will be described later. When proceeding to step 6, the CPU 11 executes a termination process and terminates the patent requirement conformity prediction process for the user. By doing so, as long as the prediction end condition is satisfied, the patent requirement suitability prediction process is automatically and continuously executed.

  Then, when proceeding to Step 5, the CPU 11 executes a patent requirement suitability prediction routine according to the flowchart shown in FIG.

  When starting the patent requirement suitability prediction routine, the CPU 11 proceeds to step 11 and adds “1” to the publication counter. In the following step 12, it is determined whether the publication counter is larger than the publication counter MAX. If not, the process proceeds to step 13. If not (when the publication counter is larger than the publication counter MAX), step 16 is executed. Proceed with the process.

  When the CPU 11 proceeds to step 13, the operation as the publication data extraction unit 101 is performed to perform data extraction according to the designated number, and the operation as the target publication extraction unit 104 is performed to extract the publication publication data. The extracted data is stored in the prediction target TR storage unit 152 and the target publication storage unit 155, respectively. Further, the CPU 11 performs the operation as the summary data extraction unit 102 to generate the above-described summary data and CT data, and stores them in the summary data storage unit 153 and the CT data storage unit 154, respectively. The target gazette extraction unit 104 extracts public gazette data whose filing date is earlier than the filing date of the prediction target application.

  Subsequently, the CPU 11 proceeds to step 14 to execute a novelty / expansion prior application prediction routine described later, and then proceeds to step 15 to execute the inventive step prediction routine. Thereafter, the CPU 11 returns to step 11 and repeats the same processing as described above. In step 16, the CPU 11 performs an operation as the prediction result editing processing unit 105 to edit and output a prediction result list L <b> 1 described later. Thereafter, the point consumption process of step 17 is executed to reduce the point balance according to the number of published applications for which the patent requirement conformity prediction has been performed. Thereafter, the patent requirement suitability prediction routine ends.

  When the CPU 11 proceeds to step 14, the CPU 11 operates as the novelty / expansion prior application prediction processing unit 125 described above, and follows the flowcharts shown in FIGS. Run the routine.

  In this case, when the CPU 11 starts the novelty / expansion prior application prediction routine, the CPU 11 proceeds to step 21, sets “0” to the document counter (document ct) and document MAX, and sets the item number counter (item ct). Set “1”. Subsequently, the process proceeds to step 22, and a full-text search is performed on the search target publication data in the target publication storage section 155 using data corresponding to the item number ct of the summary data stored in the summary data storage section 153 as a search term. The number of hit documents is set in the document MAX. In this case, since “1” is set in the item number counter in step 21, the search term is set using the data in which the item number area 153b is “1”, that is, the summary data of claim 1.

  Subsequently, the process proceeds to step 23, where it is determined whether or not there is a document hit in step 22 (whether or not document MAX is 1 or more). If there is a hit document, the process proceeds to step 24; The novelty / expansion prior application prediction routine ends.

  In step 24, “1” is added to the document counter, and in subsequent step 25, it is determined whether or not the document counter is equal to or less than document MAX. If this is true, the process proceeds to step 26, and so on. If not, the process proceeds to step 29. In step 26, whether the application publication date (hit document publication date) of the hit document is smaller than the filing date (target application date) of the prediction target application (whether hit document publication date <target application date is satisfied). ) Is determined, and if this is true, the process proceeds to step 27; otherwise, the process proceeds to step 28. In step 27, novelty / expansion prior application prediction data Nd is generated so as to include a novelty flag “N1” indicating no novelty. Thereafter, the process returns to step 24 and the same processing as described above is repeated.

  In step 28, an enlargement-first application prediction routine, which will be described later, is executed. In step 29, it is determined whether or not there is another independent term by referring to the CT data storage unit 154. If there is another independent term, the process proceeds to step 30; After the sex / expansion prior application prediction data Nd is output, the novelty / expansion prior application prediction routine ends. In step 30, the CPU 11 sets "0" in the document counter and document MAX, and a claim number larger than "1" is set in the item number counter. Thereafter, the process returns to step 22 and the same process as described above is repeated.

  On the other hand, the CPU 11 executes an enlargement-first application prediction routine according to the flowchart shown in FIG. When the extended earlier application prediction routine starts, the process proceeds to step 41, and whether or not the filing date of the hit document (document filing date) is earlier than the target filing date (reference filing date <subject filing date is satisfied) If this is true, the process proceeds to step 42; otherwise, the enlargement earlier application prediction routine is terminated. In step 42, it is determined whether or not the inventor is the same between the prediction target application and the hit document. If this is not true, the process proceeds to step 43. End the routine. In step 43, it is determined whether or not the applicant is the same between the prediction target application and the hit document. If this is not the case, the process proceeds to step 44. End the routine. Then, when the CPU 11 proceeds the process to step 44, the CPU 11 includes an enlarged first application flag “F1” indicating that the requirement of the enlarged first application (required in Article 29-2 of the Patent Law) is not satisfied. The novelty / expansion prior application prediction data Nd is generated. Thereafter, the enlargement destination application prediction routine ends.

  When the novelty / expansion prior application prediction routine is completed as described above, the process proceeds from step 14 to step 15 in FIG. 13, and the CPU 11 performs the operation as the inventive step prediction processing unit 126 to execute the inventive step prediction routine. The CPU 11 executes an inventive step prediction routine according to the flowcharts shown in FIGS.

  When starting the inventive step predictive routine, the CPU 11 advances the process to step 51, obtains the claim number of the number area 154b for the record of the independent section area 154a from the CT data storage unit 154, and It is set in the number area (No area) 165b of the independent item table 165 described later. In the subsequent step 52, the claim number of the number area 154b is obtained from the CT data storage unit 154 from a record in which the search flag of the search flag area 154e is a space and the MAX section of the MAX section area 154c is "M". Then, the minimum value (MIN) of the obtained claim number is obtained and set in the MAX counter. As shown in FIG. 9B, when there are a plurality of records whose MAX classification is “M”, the smallest claim number is set in the MAX counter.

  Then, the CPU 11 proceeds to step 53 to search the No area 165b of the independent item table 165, and in the subsequent step 54, determines whether there is a claim number larger than “1”, and “1”. Processing branches depending on whether there is a claim number larger than that. In this case, if there is no claim number greater than “1”, the process proceeds to step 55, and if it is, the process proceeds to step 56. Step 55 is a process when there is only one independent term in the claims included in the predicted application (single independent term routine), and step 56 is a process when there are multiple independent terms (multiple independent term routine). It corresponds. For example, the former corresponds to a case where the prediction target application is an application disclosed in Japanese Patent Application Laid-Open No. 2008-62282, and the latter corresponds to a case where the prediction target application is an application disclosed in Japanese Patent Application Laid-Open No. 2011-186735, for example. .

  As shown in FIG. 24, the independent term table 165 has a counter area 165a, a No area 165b, and a search flag area 165c. The counter area 165a stores a numerical value corresponding to the number of stored data. In the No area 165b, the number of the independent term is stored. A search flag is stored in the search flag area 165c. FIG. 24 shows, as an example, a case where the prediction target application is an application disclosed in Japanese Patent Application Laid-Open No. 2011-186735.

  Then, when the CPU 11 proceeds with the process to step 55, the CPU 11 executes a single independent term routine according to the flowchart shown in FIG. When the CPU 11 starts the single independent term routine, the process proceeds to step 61, and the claim number is acquired from the number area 154b for the record in which the search flag in the search flag area 154e is space from the CT data storage unit 154. Then, the minimum value (MIN) is set in the item number counter. In the subsequent step 62, an independent term search process to be described later is performed. In subsequent step 63, it is determined whether or not the search flag (search flag) is “VX” or “VY”. If the search flag is “VX” or “VY”, the process proceeds to step 64; The single independent term routine is terminated.

  When the CPU 11 advances the process to step 64, it adds “1” to the item number counter. In the next step 65, it is determined whether or not the item number counter is equal to or less than the MAX counter set in step 52. If the item number counter is equal to or less than the MAX counter, the process proceeds to step 66 to execute a dependent item search process described later. Otherwise, the independent term search process ends.

  Then, the CPU 11 executes a plurality of independent term routines according to the flowchart shown in FIG. When the CPU 11 starts the process, the process proceeds to step 52, executes the same process as described above, and then proceeds to step 55 to execute the single independent term routine in the same manner as described above. Thereafter, the CPU 11 advances the process to step 67 to determine whether or not there is a record in the CT data storage unit 154 where the search flag in the search flag area 154e is a space (that is, whether or not there is a record for which search processing has not been performed). ) Is determined, and if it is determined, the process returns to step 52 and the same processing as described above is executed. Otherwise, the plural independent term routine is terminated.

  Further, the CPU 11 executes an independent term search process according to the flowchart shown in FIG. In the independent term search processing, the CPU 11 performs the operation as the cited invention search unit 131, and performs the main cited invention search and the sub cited invention search for the independent term.

  When starting the independent term search process, the CPU 11 advances the process to step 71 to execute a main citation invention search process to be described later. In the following step 72, it is determined whether or not there is a main citation invention in the main citation invention search process (whether or not a main citation document described later is set). If there is a main citation invention, the process proceeds to step 73. If there is no main cited invention, the process proceeds to step 76. In the subsequent step 73, a sub-invention search process to be described later is executed, and in a subsequent step 74, whether or not there has been a sub-citation invention in the sub-citation invention search process (whether a sub-citation document to be described later is set). Is determined. If there is a secondary citation invention, the process proceeds to step 75, and if there is no secondary citation invention, the process proceeds to step 77.

  When the processing proceeds to step 75, the CPU 11 sets “VX” to the search flag (search flag) of the corresponding claim number, and sets “VY” to the search flag (search flag) in step 77. Further, when the CPU 11 advances the process to step 76, among the records stored in the CT data storage unit 154, the records in which the claim number in the number area 154b matches the item number counter are stored in the search flag area 154e. A search flag Ef is set to “9” indicating that the search has been completed (searched). Further, the CPU 11 generates the inventive step prediction data Vd1 so as to include the set search flag, and outputs it to the prediction result file generation unit 127. Further, the CPU 11 outputs the claim summary data ied and the concept search data Vd2 corresponding to the search result to the input vector generation unit 132. In this case, the claim summary data ied can be the summary data of the claim that is the subject of the search, but the claim that is the subject of the search of the prediction target application stored in the prediction target TR storage unit 152 It may be term data. The search flag is set to “VX” or “VY” when the main cited invention is found, but if the main cited invention is found, it is likely that the search flag does not satisfy the inventive step requirement. Therefore, whether or not the reason for refusal of the inventive step violation is found depends greatly on whether or not the main cited invention is found. By including such a search flag, the inventive step prediction data Vd1 indicates the suitability of the inventive step requirement.

  Then, the CPU 11 executes main citation invention search processing according to the flowchart shown in FIG. The main citation invention search process is a process of searching for the main citation invention closest to the prediction target invention.

  When the CPU 11 starts the main cited invention search process, the CPU 11 proceeds to step 81 and sets “0” in the development degree counter tc. Subsequently, the CPU 11 advances the processing to step 82, reads the next data from the summary data storage unit 153, and sets main search document data (document data when searching the main cited invention by concept search). One is a mandatory flag from a record in which the data type is “C” and the number of the item number area 153b corresponds to the item number counter (the item number counter is set with the minimum value of the independent item in step 61). Ef is “X”, and the degree of development Ed is the maximum value of the degree of development (expansion degree MAX) −the term of the degree of development counter tc (for example, if the degree of development MAX is “5”, the degree of development Ed is “5” −tc. The other is problem data, that is, data of a record whose data type is “P”.

  In the following step 83, the CPU 11 performs a concept search for the search target publication data stored in the target publication storage unit 155 using the search process of the main cited invention, that is, the main search document data as the input document. In this conceptual search, a vector (document vector) corresponding to each document is generated by extracting and weighting the main search document data and each document to be searched, and the inner product of each vector is obtained. Thus, the similarity is calculated. Next, in step 84, it is determined from the result of the concept search in step 83 whether or not the largest similarity is a certain value or more, and if it is more than a certain value, the process proceeds to step 85. If so, the process proceeds to step 87. In step 85, it is determined whether or not there are a plurality of documents whose similarity is equal to or greater than a certain value. If there are no documents, the process proceeds to step 86; In the main citation invention search process, the main citation is set only when there is a document whose similarity is a certain value or more.

  In step 86, the hit document is set as the main cited document (prior art document in which the main cited invention is disclosed), and the main cited invention search process ends. In step 87, “1” is added to the expansion degree counter tc, and then in step 88, it is determined whether or not the expansion degree MAX−expansion degree counter tc is “0” or less. The cited invention search process is terminated. If not, the process returns to step 82 and the above process is repeated.

  In this way, first, a concept search is performed with terms that have a degree of expansion Ed more important than the degree of expansion MAX. In the concept search, a plurality of documents can be extracted according to the similarity of documents, but when the highest similarity does not reach a certain value, there is a high possibility that the document does not correspond to the main cited document. For this reason, when a document with a similarity equal to or greater than a certain value is not found, the concept search is executed again including a term whose expansion degree Ed is smaller than the expansion degree MAX.

  In step 89, the document with the highest degree of similarity (also referred to as the most similar document) is set as the main cited document, and then the main cited invention search process ends.

  Then, the CPU 11 executes the secondary citation invention search process according to the flowchart shown in FIG. The sub-cited invention search process is a process for searching a sub-cited invention including a difference between the prediction target invention and the main-cited invention, and is executed only when the main-cited invention is found in the main-cited invention search process.

  When the CPU 11 starts the sub-cited invention search process, the process proceeds to step 91, and from the summary data storage unit 153, the data type is “C” and the number of the item number area 153b corresponds to the item number counter. Terms that are not included in the main search document data (unused search data) and data of records whose data type is “P” are read out, and they are sub-search terms (keywords for searching the sub-cited invention by full-text search) ).

  In the subsequent step 92, the CPU 11 performs a full-text search on the search target publication data stored in the target publication storage section 155 using the search process of the subcitation invention, that is, the sub search term as a search keyword. In the following step 93, it is determined whether or not there is a document hit in step 92. If there is a hit document, the process proceeds to step 94, and if not, the process proceeds to step 96. In step 94, it is determined whether or not there are a plurality of hit documents. If there are no hit documents, the process proceeds to step 95. If there are a plurality of hit documents, the process proceeds to step 98.

  In step 95, the hit document is set in the sub-cited document (prior art document in which the sub-cited invention is disclosed), and the sub-cited invention search process ends. In step 96, the sub-search term is changed and the full-text search is performed again. Here, the sub-search term is the data type “C”, the search number unused data not included in the main search document data of the record corresponding to the item number counter with the data type “C”, and the data type “ It is changed to the data of the record of “T”. In step 97, it is determined whether or not there is a hit document. If there is a hit document, the process proceeds to step 94. If not, the sub-cited invention search process is terminated. Further, in step 98, for each of the hit documents, the number of matches with the term having the data type “C” and the number of the item number area 153b corresponding to the item number counter is “X”. It is counted and the number of matches is set in the subcitation file. In the next step 99, the sub-cited files are sorted in descending order of the number of matches, and in the subsequent step 100, three sub-cited files from the top of the sub-cited file are set in the sub-cited document, and then the sub-cited invention search process ends. When a plurality of documents are hit in the sub-cited invention search, the extent to which the feature part of the prediction target invention is disclosed is examined for each of them by the number of matches with the term whose essential flag Ef is “X”. A document with a large number of matches is set as a sub-cited document.

  And CPU11 performs a dependent term search process according to the flowchart shown in FIG. The dependent term search process is executed only when the search flag (search flag) is “VX” or “VY” (when the main cited invention is found). When the CPU 11 starts the subordinate item search process, the process proceeds to step 111, and a record (item number counter) from the summary data storage unit 153 corresponding to the item number counter with the data type “C” and the item number area 153b number. In step 64, the term having the required flag Ef of “X” is read from the minimum value of the independent term in order at step 64, and this is the dependent search term (invention described in the dependent term). Is set as a keyword when searching in full-text search. In the next step 112, the CPU 11 performs a full-text search for the main cited document using the subordinate search term as a search keyword, and checks whether the invention described in the dependent claim is disclosed in the main cited document.

  In step 113, it is determined whether there is a hit document. If there is a hit document, the process proceeds to step 114. If not, the process proceeds to step 116. In step 114, "VX" is set in the search flag (search flag) of the corresponding claim number, and the hit document is set as the main cited reference of the corresponding claim number. Thereafter, the process proceeds to step 115, and among the records stored in the CT data storage unit 154, the record whose claim number in the number area 154b matches the item number counter is set in the search flag Ef in the search flag area 154e. 9 "is set, and then the dependent term search process ends. Further, in step 116, a full-text search is performed for the sub-cited document by the subordinate search term, and in the next step 117, it is determined whether or not there is a hit document. If there is a hit document, step 118 is executed and then the process proceeds to step 115. If not, the dependent term search process is terminated. In step 118, “VY” is set in the search flag (search flag) of the corresponding claim number, and the hit document is set in the sub-citation document of the corresponding claim number.

  As described above, when the novelty / expansion prior application prediction routine and the inventive step prediction routine are executed, the novelty / expansion prior application prediction data Nd and the inventive step prediction data Vd1 according to the respective results. Is output to the prediction result file generation unit 127. Further, since the requirement adequacy document vector V4 is output from the machine learning unit 133, the prediction result file generation unit 127 generates a prediction result file illustrated in FIG. 10 using these, and stores the prediction result file in the prediction result storage unit 156.

  As shown in FIG. 10, the prediction result file stores the data of each item of publication number, claim, main search document data, sub search term, search flag, hit document, and machine prediction for each prediction target application. . The machine prediction is data corresponding to the requirement conformity document vector V4 from the machine learning storage unit 133, and the reason for refusal of the inventive step violation that cited the main cited document and the sub cited document found in the inventive step prediction routine is found. The possibility is high or low (“H” when high, “L” when low).

  Further, the prediction result editing unit 105 reads the prediction result file, edits and outputs a patent requirement suitability prediction list L 1 as shown in FIG. 25, and transmits it to the user terminal device 30. The patent requirement propriety prediction list L1 includes the application publication number of the application to be predicted, the number of claims, and documents on which the suitability of requirements of novelty (expanded prior application) and inventive step is based (main cited document, sub cited document) ). “X” is described when it is predicted that the requirement of novelty (expanded prior application) and inventive step will not be met (does not meet), and “A” is recorded when it is predicted that it will meet (satisfy). These are determined by the search flag of the prediction result file.

  “H” and “L” are also written in “X” (main citation and sub-citation) and “Y” (only main citation) when predicted not to meet the inventive step requirement. (In FIG. 25, only when “H” is written together) This is in accordance with the requirement adequacy document vector V4 of the machine learning unit 133, and “H” is a violation of inventive step in the main cited document. When the possibility of refusal is likely to be issued, “L” indicates a low case.

  As described above, the patent requirement conformity prediction server 10 according to the embodiment of the present invention generates summary data from the description items of the prediction target application, and uses this to perform main citation invention search and sub-citation invention search. Yes. The main citation invention search is common to the prediction target application and its skeleton, that is, the process of searching the main citation invention closest to the prediction target invention among the prior art inventions in the summary data. Patent law and patent / utility model examination Done in line with standards. The sub-cited invention search is performed by a full-text search using a term specifying a problem to be solved by the invention or a technical field when the main cited invention is found by the main cited invention search. And patent and utility model examination standards. Therefore, in the patent requirement conformity prediction server 10 according to the embodiment of the present invention, the prediction regarding the propriety of the patent requirement is performed with the content suitable for the examination practice, so that the monitoring burden of the patent application can be effectively reduced.

  On the other hand, as described above, the patent requirement suitability prediction processing unit 103 has the machine learning unit 133, and the machine learning unit 133 is constructed by an artificial intelligence program trained with learning data based on past examination results. ing.

  By the way, about 320,000 or more patent applications are filed annually on a performance basis in 2014, and the 1st action has already been issued for some or many patent applications before that. Among them, there are many applications (progressive rejection applications) in which the reasons for refusal of violation of inventive step are pointed out in the notice of reasons for refusal.

  In the inventive step rejection application, the examination results differed between the invention described in the claim at the time of examination and the main cited invention. However, the examiner determined that there was an inventive step based only on the difference. It means that there was no. On the other hand, in patent applications, applications for which a patent assessment was issued without the first action being issued, or a reason for refusal was issued, but the reasons for refusal of the inventive step violation were pointed out. There are applications that did not exist (applications without inventive step rejection).

Then, for example, as shown in FIG. 23, if there is a patent application Pd to be examined and its filing date is t ₀ , the main cited invention or sub-cited invention for the patent application Pd can be known or publicly used. are known from the literature and the Internet known invention is primarily (in FIG. 23, rf1~rf6) filed t ₀ Patent Laid-open application previously have been published from the invention disclosed in.

  Here, it is assumed that, as a result of examination, it is determined that the invention disclosed in the publication rf6 corresponds to the main cited invention. In this case, although there is a difference between the invention according to the patent application Pd and the invention disclosed in the publication rf6, the distance dp corresponding to the difference is the inventive step of the invention according to the patent application Pd. It is thought that it was not large enough to affirm. On the other hand, if it is determined that the invention disclosed in the publication rf6 does not fall under the main cited invention, it is considered that the distance dp is large enough to affirm the inventive step of the application related to the application Pd. It is done.

  If it is possible to determine how much the difference is when the inventive step is affirmed and what is the difference when the invention is denied, it can be considered as an objective judgment material for whether or not the patent requirement is met. In view of the above, for that purpose, it is considered effective to determine the distance dp according to the difference between the two inventions. The machine learning unit 133 determines this by learning the training data based on the past examination results, and gives a measure of whether the inventive step is highly likely to be denied or low.

  In the learning of the machine learning unit 133, in the invention according to the present application (the invention of the present application), the distance dp is regarded as a difference between two document vectors, and the distance dp is learned when there is a reason for refusal of inventive step and when there is no reason for rejection. Therefore, learning is performed using the training data based on the above-described HL pattern.

  Then, when predicting the suitability of patent requirements, the gist data is obtained for the prediction target application, and the most similar document is searched by using the concept data. Since the most similar document has the document vector having the highest similarity to the document vector of the prediction target application (more precisely, the document vector obtained from the description of the independent item), it is the main document in the published application. It is recognized that it is most likely to be cited.

  The difference between the citation candidate vector RfV obtained from the most similar document and the summary vector EV obtained from the summary data of the prediction target application is obtained to generate a summary movement vector V3, which is input to the machine learning unit 133, Whether or not there is a reason for refusal of inventive step violation that cites the main cited document found in the main cited invention search is output. As a result, it is possible to give an indication of whether the reason for refusal of violating the inventive step is high or low.

  As described above, the patent requirement suitability prediction server 10 includes the machine learning unit 133, so that the patent requirement suitability is predicted in a manner that reflects the examination results of the Patent Office. Since the judgment results of artificial intelligence can be used for judgment results that must rely solely on the experience and intuition of experts such as examiners and patent attorneys as before, it is possible to make the prediction results objective Therefore, it can be expected that business efficiency will be improved in combination with reduction of the monitoring burden of other company's applications and more efficient judgment of whether or not to request examination of in-house applications.

  Further, the inventive step prediction processing unit 126 performs a concept search in the main citation invention search and performs a full text search in the sub citation invention search. Whether or not there is a reason for refusal to violate the inventive step largely depends on whether or not the main cited invention is found, but if a full text search is performed in the main cited invention search to find the main cited invention, there is a possibility that multiple documents will be hit In some cases, the main cited invention (main cited document) cannot be specified. In this regard, in the concept search, similar documents are ordered according to the similarity obtained from the inner product of the document vectors. Therefore, the main cited document can be specified by selecting the document having the highest similarity. By combining the prediction by the machine learning unit 133 with the main citation document found in this way, it is possible to predict whether the reason for refusal of the inventive step violation that cited the main citation document is high or low. In addition, it is possible to clarify whether there is a sub-cited document by performing a full text search by sub-cited invention search.

  In the above description, as a more preferred embodiment, a case where the cited invention search unit 131 of the inventive step prediction processing unit 126 has a main cited invention search unit and a sub-cited invention search unit is shown. As described above, when the main cited invention is found by the main cited invention search, there is a high possibility that the reason for refusal without inventive step will be found. The generation unit 132 and the machine learning unit 133 may be operated to output the requirement suitability document vector V4. Even in this case, by using together the inventive step prediction data Vd1 related to the main cited document set in step 89 and the requirement suitability document vector V4 generated by the machine learning unit 133, the content suitable for the examination practice can be obtained. Since the prediction can be performed and the prediction uses the judgment result of the artificial intelligence, the prediction result can have objectivity. Therefore, it is sufficient that the inventive step prediction processing unit 126 has the main citation invention search unit and does not have to have the sub citation invention search unit, but as described above, the progress having the sub citation invention search unit. The sex prediction processing unit 126 is more preferable.

Second Embodiment Subsequently, a patent requirement suitability prediction server 200 according to a second embodiment will be described with reference to FIGS. 26 to 30. As shown in FIG. 26, the patent requirement suitability prediction server 200 is replaced with the patent requirement suitability prediction processing unit 103, the prediction result editing processing unit 105, and the prediction result storage unit 156, as compared with the patent requirement suitability prediction server 10 described above. 3 further includes a patent requirement suitability prediction processing unit 203, a prediction result editing processing unit 205, and a prediction result storage unit 256, and a point that the prediction result list L2 is output instead of the prediction result list L1.

  As shown in FIG. 27, the patent requirement suitability prediction processing unit 203 is different from the patent requirement suitability prediction processing unit 103 in that an inventive step prediction processing unit 226 is used instead of the inventive step prediction processing unit 126 and the prediction result file generation unit 127. And the prediction result file generation unit 227 is different.

  And the inventive step prediction processing unit 226 is different from the inventive step prediction processing unit 126 in that it has a cited invention search unit 231 and a machine learning unit 233 instead of the cited invention search unit 131 and the machine learning unit 133, and an input The difference is that the operation of the vector generation unit 132 is different.

In the inventive step predictive processing unit 126 according to the first embodiment described above, only the most similar document is set as the main cited document by performing the main cited invention search (step 89). In the inventive step predictive processing unit 226, n documents including the most similar documents in descending order of similarity (n is an integer of 2 or more) are extracted as similar documents, and these similar documents are used as main cited documents. It is set. In addition, the machine learning unit 233 classifies the _n summary movement vectors V3 _{1 to} V3 _n into three classes of S class, H class, and L class, which will be described later.

The cited invention search unit 231 has a main cited invention search unit and a sub-cited invention search unit similar to the cited invention search unit 131, but the operation of the main cited invention search unit compared to the cited invention search unit 131. Are different, and the output data is also different. The cited invention search unit 131 sets the most similar document as the main cited document by the main cited invention search unit performing the main cited invention search (step 89 of the above-described main cited invention search process). In step 89, the main citation invention search unit of the search unit 231 extracts n documents including the most similar documents in descending order of similarity as similar documents, and sets them as the main cited documents (doc _{1 to} doc _n ). To do. The main cited invention with the operation of the search part vary, and generates n matter of inventive step prediction data Vd1 ₁ ~Vd1 _n corresponding the CPU11 at step 76 in independent claim retrieval processing described above to each similar document, They are output to the prediction result file generation unit 227. Further, in the independent claims search process, CPU 11 is output to the claims subject matter data ied to the input vector generating unit 132, a concept search data _Vd2 1 _{~Vd2 n} of n matter in accordance with the similar documents to the input vector generator 132 Output.

Compared with the machine learning unit 133, the machine learning unit 233 performs n pieces of abstract movement vectors V3 ₁ to V3 ₁ corresponding to each similar document by machine learning (supervised learning) using the SHL pattern described below as a learning pattern. V3 _n is classified into one of S class, H class, and L class, respectively, and n output signals (requirement conformity document vectors V4 _{1 to} V4 _n ) corresponding to the classification result are output. . The S class, the H class, and the L class are classes that are highly likely not to meet the inventive step requirement, classes that are highly unlikely to fit, and conforming classes (the reason for refusal of inventive step violations for the predicted application). Class that is very likely to be found, a high class, a class that is not found).

The SHL pattern is a combination of the following three patterns S, H, and L.
Pattern S: The learning document vector is the first learning document vector, and the teacher vector is a vector indicating that there is a reason for rejection of novelty and inventive step (for example, only the dimension corresponding to the correct class is "1" and the others are "0") Combination pattern H with “vector” of: the learning document vector is the second learning document vector, the teacher vector is a vector indicating the reason for refusal of inventive step and no reason for refusal of novelty (for example, the above corresponding to the correct class) A combination pattern L: a vector in which the learning document vector is the third learning document vector and the teacher vector has no reason for refusal of inventive step. For example, it is a combination pattern with a vector whose only dimension different from the above two is “1” and the other is “0”.

  The first learning document vector is an application for which the first notice of reasons for refusal (1st action) has been issued as a result of examination by the Patent Office in a published application, and the same document is cited in the 1st action. An application (novelty / inventive step) in which the reason for refusal of violation of novelty or inventive step (the reason for refusal that the requirements of Article 29 (1) (iii) and Article 2 (2) of the Patent Act are not met) was pointed out The document vector corresponding to the claim (at the time of issuance of the reason for refusal) where the reason for refusal of the application for refusal was pointed out, and the cited reference 1 at that time (the first main cited publication cited as the main publication) The first moving document vector corresponding to the difference from the document vector corresponding to the object (first quoted document vector).

  The second learning document vector is an application in which the first notice of reasons for refusal (1st action) is issued as a result of examination by the Patent Office in the published application, and the reason for refusal of novelty ( The reason for refusal to violate the inventive step (rejection not satisfying the requirement of paragraph 2 of the same Article) is not pointed out, but the reason for refusal of violating the inventive step is not pointed out The document vector corresponding to the claim (at the time of issuance of the reason for refusal) and the cited reference 1 (main publication) where the reason for refusal of the application (reasonable refusal application) was pointed out The second moving document vector corresponding to the difference from the document vector (second cited document vector) corresponding to the second main cited publication cited as.

  The third learning document vector is the result of examination in the published application, where the first action is not issued and the patent decision is issued (non-rejection application) or the first action is issued but progresses to the reason for refusal Document vectors according to claim 1 (at the time of the notice of reasons for refusal) of applications for which no reason for refusal of sex violation has been pointed out (applications without inventive refusal), and those applications without refusal or inventive refusal As a result of the concept search for the application, a third moving document vector corresponding to the difference from the document vector (non-cited document vector) corresponding to the document (the most similar document for learning) that is considered to have the highest similarity. is there.

  As with the machine learning unit 133, the machine learning unit 233 can apply a neural network modeled on a cranial nerve network for information processing, and preferably uses a BP (back propagation) network among them.

As shown in FIG. 28, the input vector generation unit 132 of the inventive step prediction processing unit 126 includes a gist vector generation unit 132a, a citation candidate vector generation unit 132b, and a movement vector generation unit 132c. Among them, the operations of the citation candidate vector generation unit 132b and the movement vector generation unit 132c are different. That is, reference candidate vector generation part 132b, since the concept search data Vd2 ₁ ~Vd2 _n of n matter from the cited invention search unit 231 is input, and inputs the publication data of each similar documents included in that each of which Feature words are extracted and weighted according to each word to generate _n document vectors (citation candidate vectors) RfV _{1 to} RfV _n corresponding to each similar document. Movement vector generation unit 132c includes a summary vector EV, the difference between the reference candidate vectors _RfV 1 _{~RfV n} by calculating the n matter gist movement vector _V3 1 to V3 _n for corresponding to the difference between both the document vector Generate.

As described above, since each similar document is a document extracted in descending order from the highest similarity by the concept search by the main cited invention search unit, all of them are the examination of the prediction target invention, and the disclosure of the main cited invention is disclosed. It is estimated that the probability of being cited as a document is high. Therefore, if the candidate documents RfV _{1 to} RfV _n are obtained by using each similar document as a citation candidate and the difference between the citation candidate vectors RfV _{1 to} RfV _n is calculated to obtain the gist movement vectors V3 _{1 to} V3 _n , the prediction target invention, Abstract movement vectors V3 _{1 to} V3 _n corresponding to differences from the invention disclosed in similar documents are generated.

  Compared with the prediction result file generation unit 127, the prediction result file generation unit 227 generates a prediction result file having the layout shown in FIG. 29 and stores the prediction result file in the prediction result storage unit 256. The difference is that the operation as the non-conformance rate calculating unit according to the embodiment is performed to calculate the non-conformance rate Vr related to the prediction target application.

The non-conformance rate Vr indicates the possibility of not meeting the inventive step requirement for the prediction target application, and indicates the possibility of finding the reason for refusal of the inventive step violation for the prediction target application. The requirement adequacy document vectors V4 _{1 to} V4 _n output from the machine learning unit 233 are generated with contents that are highly likely to be incompatible with the requirement of inventive step, are high, and are not included. It shows the possibility of finding reasons for refusal of violation of inventive step in relation to the literature. Therefore, using these, the prediction result file generation unit 227 calculates the non-conformance rate Vr related to the prediction target application. In this case, the prediction result file generation unit 227 calculates the non-conformance rate Vr according to the non-conformance rate calculation rule. The non-conformance rate calculation rule is a rule by which the prediction result file generation unit 227 calculates the non-conformance rate Vr. In the present embodiment, the S class included in the requirement conformity document vectors V4 _{1 to} V4 _n , The calculation rule table (not shown) is set so that the numerical value of the non-conformance rate Vr is determined according to the number of cases of the H class and the M class. The non-conformance rate calculation rule can be set as follows, for example.

2 or more S class: Vr ≧ 85%
There is one S class and the number of H class is 50% or more: Vr ≧ 75%
One S class and less than 50% H class: Vr ≧ 65%
S class is 0, H class is more than 50%: Vr ≧ 50%
S class is 0, H class is less than 50%: Vr ≧ 40%
0 for both S and H classes: Vr ≧ 15%

  According to the non-conformance rate calculation rule, for example, when there are five similar documents (the above-mentioned integer n is “5”) and there are two S classes, Vr ≧ 85%. Also, if there is one S class and three H classes, Vr ≧ 75%, but if there are two H classes, Vr ≧ 65%, both S class and H class are zero (all cases are L class) ) Vr ≧ 15%.

  29, the prediction result file generated by the prediction result file generation unit 227 includes a non-conformance rate Vr as compared to the prediction result file generated by the prediction result file generation unit 127. Is different.

  Further, the prediction result editing processing unit 205 is different from the prediction result editing processing unit 105 in that it reads a prediction result file, and edits and outputs a patent requirement suitability prediction list L2 as shown in FIG. . The patent requirement suitability prediction list L2 is different from the patent requirement suitability prediction list L1 in that an OA rate is added. The OA rate indicates the possibility that a reason for refusal that violates patent requirements (novelty or inventive step) will be found in the examination process and a notice of reason for refusal indicating this will be issued. A numerical value corresponding to the non-conformity rate Vr is shown.

As described above, in the patent requirement suitability prediction server 200 according to the second embodiment, the cited invention search unit 231 includes the most similar documents in the inventive step predictive processing unit 226 of the patent requirement suitability prediction processing unit 203. Is set as the main cited document. In addition, the machine learning unit 233 classifies the abstract movement vectors V3 _{1 to} V3 _n corresponding to each similar document into three classes of S class, H class, and L class, and the requirement conformity document vector V4 ₁ to V class according to the classification result. V4 _n is output.

  In the patent requirement conformity prediction server 10 according to the first embodiment, the prediction regarding patent requirement conformity is performed in a form that conforms to examination practice and reflects examination results of the Patent Office. This also applies to the patent requirement suitability prediction server 200.

  However, in the patent requirement suitability prediction server 10, only the most similar document is extracted as the main cited document in the main cited invention search. Since the most similar document is a document having the highest similarity to the prediction target invention as a result of the concept search, it is considered that the most similar document is most likely cited as the main cited document as a result of the actual examination. However, the most similar document is not always cited in the actual examination, and there is very little difference in similarity between the most similar document and the next similar document (next similar document) It is fully conceivable that the next similar document is more appropriate as the main cited document than the most similar document. Therefore, if a plurality of documents including the most similar documents are extracted in the main cited invention search, and the document vectors are classified by the machine learning unit 233 for these documents, whether or not the patent requirement is met in consideration of the next similar documents. Predictions are made. Therefore, the prediction accuracy of the patent requirement suitability prediction server 200 is improved more than the prediction accuracy of the patent requirement suitability prediction server 10.

In actual examination practice, when a reason for refusal of inventive step violation is found for a patent application, the reason for refusal of inventive step violation and the reason for refusal of novelty violation is the same document (the document cited in this case is newly May also be pointed out by quoting refusal documents of sex / inventive step rejection). In such a case, since the examiner determines that there is no difference between the invention according to the claims of the patent application and the invention disclosed in the novelty / inventive step rejection citation, the summary movement vector V3 _When document vectors classified into the S class are included in _{1 to} V3 _n , it is considered that the possibility of finding the reason for refusal of the inventive step violation is higher than the case where it is not. Therefore, by constructing the machine learning unit 233 by performing machine learning using the SHL pattern so that the distance dp viewed from the novelty / inventive rejection application and the distance dp viewed from the inventive rejection application can be distinguished, It is possible to make a prediction that distinguishes between cases where the reason for refusal of an inventive step violation is very likely and cases where it is not. By doing so, it is possible to expect improvement in prediction accuracy by the patent requirement suitability prediction server 200 and further improvement in business efficiency.

(Modification 1)
In the inventive step prediction processing unit 226, one machine learning unit 233 classifies _n summary movement vectors V3 _{1 to} V3 _n . However, the progress in the patent requirement suitability prediction processing unit 213 shown in FIG. as sex prediction processing unit 227 includes a plurality of machine learning unit ₂₃₃ 1 _{~233 n} corresponding to the subject matter movement vector _V3 1 to V3 _n, each of which is adapted to classify the subject matter movement vector _V3 1 to V3 _n May be. Further, although not shown, a plurality of input vector generation units 132 may be provided according to the number of concept search data Vd2 _{1 to} Vd2 _n . By doing so, each of the machine learning units 233 _{1 to} 233 _n or each of the input vector generation units 132 executes the processing in parallel, so that the processing time can be shortened.

(Modification 2)
In each of the embodiments described above, an example in which the patent requirement suitability prediction server 10 or 200 functions as a patent requirement suitability prediction device by installing the patent requirement suitability prediction program in the patent requirement suitability prediction server 10 or 200 will be described. To explain. In addition, the present invention is also applicable to the case where the user terminal device 30 functions as a patent requirement suitability prediction device. In this case, the above-described patent requirement suitability prediction program is changed according to at least the following changes 1) and 2), and the changed patent requirement suitability prediction program is transferred from the patent requirement suitability prediction servers 10 and 200 to the user terminal device. It may be downloaded to 30 and installed in the user terminal device 30.

Modification 1) Image data for performing an input operation such as a designated number is displayed on the user terminal device 30 without being transmitted from the patent requirement suitability prediction servers 10 and 200 to the user terminal device 30.
Modification 2) The user terminal device 30 outputs a patent requirement suitability prediction list.

  The above description is the description of the embodiment of the present invention, and does not limit the apparatus and method of the present invention, and various modifications can be easily implemented. In addition, an apparatus or a method configured by appropriately combining components, functions, features, or method steps in each embodiment is also included in the present invention.

  For example, the user terminal device may be a notebook computer or a PDA instead of a high-function mobile phone or a tablet-type terminal device. The patent requirement suitability prediction program executed by the CPU 11 can be recorded on various recording media such as a magnetic recording medium, a CD-ROM, and a DVD, and can also be downloaded from a server (not shown) via a network.

  By applying the present invention, prediction regarding the suitability of patent requirements is made with contents that are suitable for examination practice, and the monitoring burden can be effectively reduced. The present invention can be used in the field of patent requirement suitability prediction apparatus and patent requirement suitability prediction program.

  DESCRIPTION OF SYMBOLS 1 ... Patent requirement suitability prediction system, 10,200 ... Patent requirement suitability prediction server, 11, 31 ... CPU, 30 ... User terminal device, 101 ... Extraction unit, 102 ... Abstract data extraction unit, 103, 203, 213 ... Patent requirement Appropriateness prediction processing unit, 105 ... prediction result editing processing unit, 125 ... novelty / expanded prior application prediction processing unit, 126, 226, 227 ... inventive step prediction processing unit, 132 ... input vector generation unit, 132a ... abstract vector generation unit , 132b ... citation candidate vector generation unit, 132c ... movement vector generation unit, 133, 233 ... machine learning unit, 153 ... gist data storage unit, 154 ... CT data storage unit, 156, 256 ... prediction result storage unit, L1, L2 … Predicted result list.

Dependency analysis unit 116 performs receiving dependency analysis principal part data stored in the main part data storage unit 162, and outputs the result to the pattern data extraction unit 117.

The pattern data extraction unit 117 inputs the analysis result of the dependency analysis unit 116, and includes a noun immediately preceding “Hi” in hiragana, a character string that is a combination of the corresponding verb, and the beginning of the names of the inventions. (First name) is output. For example, in a sentence including the character string “present invention” in the column “Problem to be Solved by” of Japanese Patent Application Laid-Open No. 2008-62282, the noun immediately before “O” in hiragana and the corresponding Verb combinations include “adjustment” and “do not do”, “concentricity” and “obtain”, “precision punching” and “provide”. These are output from the pattern data extraction unit 117. In the present embodiment, among the data output from the pattern data extraction unit 117, the data extracted from the “problem to be solved by the invention” column corresponds to the problem data. For example, the data type of FIG. Data such as a record of “P” can be used.

Next, the CPU 11 proceeds to step 4 to determine whether or not a prediction end condition is satisfied. Here, the CPU 11 proceeds to step 6 when the prediction end condition is satisfied, but proceeds to step 5 otherwise. When proceeding to step 5, the CPU 11 executes a patent requirement suitability prediction routine which will be described later. When proceeding to step 6, the CPU 11 executes a termination process and terminates the patent requirement conformity prediction process for the user. By doing so , the patent requirement suitability prediction process is automatically and continuously executed until the prediction end condition is satisfied.

Claims (4)

Gazette data extracting means for extracting prediction target data corresponding to a designated number from a published gazette data storage unit in which electronic data of a published patent gazette is stored as published gazette data;
Term data that indicates terms that can specify the gist of the invention to be predicted disclosed in the application to be predicted, which is specified by the data to be predicted extracted by the publication data extraction means, and is at least Summary data extraction means for extracting from the prediction target data, data including feature part data extracted from the feature part of each claim and problem data extracted from the column of the problem to be solved by the invention;
Summary data storage means for storing the summary data extracted by the summary data extraction means;
The publication data is searched using the summary data stored in the summary data storage means, and novelty prediction data indicating whether the novelty requirement of the prediction target invention is appropriate is generated according to the search result. Novelty prediction processing unit, inventive step prediction processing unit for generating inventive step prediction data indicating whether or not the inventive step requirements are appropriate, and the prediction target invention using the novelty prediction data and the inventive step prediction data A patent result suitability prediction processing means having a prediction result file generation unit for generating a prediction result file indicating whether or not the patent requirement is suitable,
The inventive step prediction processing unit includes a main citation invention search unit that searches for a main citation invention closest to the prediction target invention among prior art inventions specified by the publication gazette data, and a document classification that classifies document vectors And
The main cited invention search unit targets the publication gazette data with the feature portion data and the problem data of each claim among the summary data stored in the summary data storage means as main search document data. Performing a concept search, and as a result of the concept search, the most similar document with the highest similarity is set as the main cited document in which the main cited invention is disclosed,
The document classification unit classifies an input summary movement vector as to whether or not it meets the requirement of inventive step by machine learning using a plurality of training data including a learning document vector and a teacher vector. It is constructed so as to output a requirement suitability document vector according to the classification result, and the summary movement vector includes a summary vector according to each claim of the prediction target application, and a citation candidate vector according to the most similar document. Patent requirement conformity prediction device which is a vector corresponding to the difference between the two. Gazette data extracting means for extracting prediction target data corresponding to a designated number from a published gazette data storage unit in which electronic data of a published patent gazette is stored as published gazette data;
Term data that indicates terms that can specify the gist of the invention to be predicted disclosed in the application to be predicted, which is specified by the data to be predicted extracted by the publication data extraction means, and is at least Summary data extraction means for extracting from the prediction target data, data including feature part data extracted from the feature part of each claim and problem data extracted from the column of the problem to be solved by the invention;
Summary data storage means for storing the summary data extracted by the summary data extraction means;
The publication data is searched using the summary data stored in the summary data storage means, and novelty prediction data indicating whether the novelty requirement of the prediction target invention is appropriate is generated according to the search result. Novelty prediction processing unit, inventive step prediction processing unit for generating inventive step prediction data indicating whether or not the inventive step requirements are appropriate, and the prediction target invention using the novelty prediction data and the inventive step prediction data A patent result suitability prediction processing means having a prediction result file generation unit for generating a prediction result file indicating whether or not the patent requirement is suitable,
The inventive step prediction processing unit includes a main citation invention search unit that searches for a main citation invention closest to the prediction target invention among prior art inventions specified by the publication gazette data, and a document classification that classifies document vectors And
The main cited invention search unit targets the publication gazette data with the feature portion data and the problem data of each claim among the summary data stored in the summary data storage means as main search document data. A concept search is performed, and as a result of the concept search, a plurality of documents including the most similar document having the highest similarity in descending order of similarity are extracted as similar documents, and the main cited invention is disclosed for each similar document. As the main cited reference
The document classification unit is a class that has a high possibility that the input summary movement vector does not conform to the requirement of inventive step by machine learning using a plurality of training data including a learning document vector and a teacher vector, a high class, It is constructed so as to be classified into one of the classes that meet the requirement of the inventive step and to output a requirement conformity document vector according to the classification result, and the gist movement vector corresponds to each claim of the prediction target application A plurality of vectors according to the difference between the abstract vector and each citation candidate vector corresponding to each similar document,
The patent requirement conformity prediction processing means calculates a non-conformance rate indicating a possibility of not conforming to the inventive step requirement for the prediction target application according to a plurality of the requirement conformity document vectors output from the document classification unit. A patent requirement conformity prediction device further comprising a non-conformance rate calculation unit for calculating. The document classification unit includes a combination of the learning document vector as the training data, the learning document vector being a first learning document vector, the teacher vector being a vector indicating that there is a reason for rejection of novelty and inventive step, and the learning document vector being a first learning document vector. A combination of the learning vector of 2 with a vector indicating that the teacher vector has a reason for refusal of inventive step and no reason for refusal of novelty, and the learning document vector is a third learning document vector and the teacher vector has an inventive step. A combination with a vector indicating no reason for refusal is used,
The first learning document vector is an application in which a notice of reasons for refusal has been issued among published applications that have already been published, and the novel document has no novelty or inventive step by citing the same document in the notice of reasons for refusal The document vector corresponding to the claim for which the reason for refusal was pointed out in the novelty / inventive step refusal application in which the reason for refusal was pointed out, and the first main cited publication which is the above-mentioned document cited for the reason for refusal A first moving document vector corresponding to a difference from the first cited document vector corresponding to the object,
The second learning document vector is an application for which a notice of reason for refusal is issued in the published application, and the reason for refusal of novelty is not pointed out in the notice of reason for refusal, but there is a reason for refusal of inventive step. The document vector corresponding to the claim in which the reason for refusal of the inventive step rejection application pointed out was pointed out, and the second corresponding to the second main cited publication cited as the main publication for the reason for refusal A second moving document vector corresponding to the difference from the cited document vector of
The third learning document vector is a non-rejection application for which a patent decision has been issued without a notice of reason for refusal being issued or an application for which a notice of reason for refusal has been issued in the published application, the notice of reason for refusal And the document vector according to claim 1 of the non-progressive refusal application for which the reason for refusal of inventive step was not pointed out, and the result of the concept search for the non-refusal application or the non-progressive refusal application, The patent requirement conformity prediction apparatus according to claim 2, wherein the third requirement is a third moving document vector obtained from a difference from a non-cited document vector corresponding to the most similar document for learning that is said to be high. A patent requirement conformity prediction program for causing a computer to function as a patent requirement conformity prediction device, wherein the computer designates a specified number from a published gazette data storage unit in which electronic data of a published patent gazette is stored as published gazette data Gazette data extraction means for extracting prediction target data according to
Term data that indicates terms that can specify the gist of the invention to be predicted disclosed in the application to be predicted, which is specified by the data to be predicted extracted by the publication data extraction means, and is at least Summary data extraction means for extracting from the prediction target data, data including feature part data extracted from the feature part of each claim and problem data extracted from the column of the problem to be solved by the invention;
Summary data storage control means for storing the summary data extracted by the summary data extraction means;
Novelty prediction data which searches the publication gazette data using the summary data stored by the control of the summary data storage control means, and indicates whether the novelty requirement of the prediction target invention is appropriate according to the search result A novelty prediction processing unit that generates the inventive step, an inventive step prediction processing unit that generates the inventive step prediction data indicating whether or not the inventive step meets the requirements of the inventive step, and the novelty prediction data and the inventive step prediction data Function as a patent requirement suitability prediction processing means having a prediction result file generation unit for generating a prediction result file indicating the patent requirement suitability of the invention to be predicted;
Among the prior art inventions in which the inventive step prediction processing unit is specified by the publication data, a main citation invention search unit that searches for a main citation invention that is closest to the prediction target invention, and a document classification unit that classifies document vectors And
The main cited invention search unit targets the publication gazette data with the feature portion data and the problem data of each claim among the summary data stored under the control of the summary data storage control means as main search document data The most similar document with the highest similarity as a result of the concept search is the main cited document in which the main cited invention is disclosed,
The document classification unit classifies the input summary movement vector as one that meets the requirement of inventive step by machine learning using a plurality of training data including a learning document vector and a teacher vector. It is constructed so as to output a requirement suitability document vector according to the classification result, and the summary movement vector includes a summary vector according to each claim of the prediction target application, and a citation candidate vector according to the most similar document. Patent requirement propriety prediction program which is a vector corresponding to the difference between the two.

Images